Optimization methods in diagnostics problems

K. I. Anan'ev ; V. V. Demyanova ; V. F. Dem'yanov ; A. V. Kokorina ; S. Ya. Svistun ; I. S. Stegalin

Vestnik Sankt-Peterburgskogo universiteta. Prikladnaâ matematika, informatika, processy upravleniâ, no. 3 (2011), pp. 3-12

Résumé

Some results of the studies obtained by making use of nonsmooth discriminant analysis (NDA) are discussed. This tool represents the optimization approach. Algorithms based on NDA turn out to be quite competitive and efficient. NDA employs, among others, methods of nonsmooth analysis and nondifferentiable optimization. Natural criterion functionals, their approximations (surrogate functionals) as well as the main expert method are desсribed in the paper. By means of the approach presented, a database of the patients of a psychiatric hospital treated due to schizophrenia is analyzed.

Détail

Keywords: mathematical diagnostics, optimization, nonsmooth analysis, natural and surrogate functionals, main expert method.

Bibliographie

[1] Amosov N. M., Zaitsev N. G., Melnikov A. A. i dr., Meditsinskaya informatsionnaya sistema, Naukova dumka, Kiev, 1971, 307 pp.

[2] Genkin A. A., Novaya informatsionnaya tekhnologiya analiza meditsinskikh dannykh, Programmnyi kompleks OMIS, Politekhnika, SPb., 1999, 191 pp.

[3] Zhuravlev Yu. I., Dmitriev A. N., Krendelev F. N., “O matematicheskikh printsipakh klassifikatsii predmetov i yavlenii”, sb. trudov In-ta matematiki Sib. otd. AN SSSR (Novosibirsk), Diskretnyi analiz, 7, 1966, 3–15 | Zbl

[4] Vapnik V. N., Chervonenkis A. Ya., Teoriya raspoznavaniya obrazov (statisticheskie problemy obucheniya), Nauka, M., 1974, 415 pp.

[5] Golovkin B. A., Mashinnoe raspoznavanie i lineinoe programmirovanie, Sovetskoe radio, M., 1973, 99 pp. (Biblioteka tekhn. kibernetiki)

[6] Mangasarian O. L., “Misclassification minimization”, J. of Global Optimization, 5 (1994), 309–323 | DOI | MR | Zbl

[7] Mangasarian O. L., “Mathematical programming in data mining”, Data Mining and Knowledge Discovery 1, 1 (1997), 183–201 | DOI

[8] Lee Y.-J., Mangasarian O. L., “SSVM: A Smooth Support Vector Machine for Classification”, Computational Optimization and Applications, 20:1 (2001), 5–22 | DOI | MR | Zbl

[9] Bagirov A. M., Rubinov A. M., Soukhoroukova N. V., Yerwood J., “Unsupervised and Supervised Data Classification Via Nonsmooth and Global Optimization”, TOP, 11:1 (2003), 1–93 | DOI | MR | Zbl

[10] Demyanov V. F., “Mathematical diagnostics via nonsmooth analysis”, Optimization Methods and Software, 20:2–3 (2005), 197–218 | DOI | MR | Zbl

[11] Demyanova V. V., “Prognozirovanie effektivnosti razlichnykh sposobov lecheniya”, Vestn. S.-Petepb. un-ta. Sep. 10: Prikladnaya matematika, informatika, protsessy upravleniya, 2007, no. 4, 3–16

[12] Demyanov V. F., Demyanova V. V., Kokorina A. V., Moiseenko V. M., “Prognozirovanie effektivnosti khimioterapii pri lechenii onkologicheskikh zabolevanii”, Vestn. S.-Petepb. un-ta. Sep. 10: Prikladnaya matematika, informatika, protsessy upravleniya, 2006, no. 4, 30–36

[13] Demyanova V. V., “Odnomernaya identifikatsiya metodom razdeleniya”, Vestn. S.-Petepb. un-ta. Sep. 10: Prikladnaya matematika, informatika, protsessy upravleniya, 2006, no. 3, 28–31

[14] Kokorina A. V., “Ranking the Parameters in Classification Databases”, Longevity, Aging and Degradation Models, (Matepialy Mezhdunap. konfepentsii LAD'2004), v. 2, Izd-vo S.-Petepb. gos. politekh. un-ta, SPb., 2004, 191–193

[15] Ananev K. I., “Optimizatsionnye metody v zadachakh identifikatsii i ranzhirovaniya”, Protsessy upravleniya i ustoichivost, Trudy 41-i Mezhdunar. nauch. konferentsii aspirantov i studentov, eds. N. V. Smirnov i G. Sh. Tamasyan, Izdat. Dom S.-Peterb. gos. un-ta, SPb., 2010, 257–260

[16] Stegalin I. S., “Klasternye metody optimizatsii v zadachakh identifikatsii i ranzhirovaniya”, Protsessy upravleniya i ustoichivost, Trudy 41-i Mezhdunar. nauch. konferentsii aspirantov i studentov, eds. N. V. Smirnov i G. Sh. Tamasyan, Izdat. Dom S.-Peterb. gos. un-ta, SPb., 2010, 298–301

[17] Demyanova V. V., “The Principal Expert Method in Data Mining”, Applied Comput. Math., 4:1 (2005), 70–74 | MR | Zbl

[18] Demyanova V. V., “Metod glavnogo eksperta v zadachakh identifikatsii”, Trudy Mezhdunar. konferentsii «Ustoichivost i protsessy upravleniya» ((S.-Peterburg, 29.06.2005–01.07.2005)), v. 2, eds. D. A. Ovsyannikov, L. A. Petrosyan, Izd-vo S.-Peterb. un-ta, SPb., 2005, 815–822

[19] Grigoreva K. V., Approksimatsiya kriterialnogo funktsionala v zadachakh matematicheskoi diagnostiki, dis. na soiskanie uchen. stepeni kand. fiz.-mat. nauk, S.-Peterb. gos. un-t, SPb., 2006, 191 pp.

[20] Zubova O. A., Metody negladkogo analiza v zadachakh identifikatsii i diagnostiki, dis. na soiskanie uchen. stepeni kand. fiz.-mat. nauk, S.-Peterb. gos. un-t, SPb., 2008, 95 pp.